AI Paper Atlas

Research map / Detection and segmentation / CNN features

Gradient-Induced Co-Saliency Detection

Zhao Zhang, Wenda Jin, Jun Xu, Ming-Ming Cheng

ECCV 2020 · Detection and segmentation › CNN features · approach: RGB salient object detection · 126 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GIM to the baseline (ablation)SOD baseline · CoCAF_avg: 0.420 -> 0.446Improved
add ARM to the baseline without GIM (ablation)SOD baseline · CoCAF_avg: 0.420 -> 0.429No clear effect
add ARM to GIM (ablation)GICD without JT · CoCAF_avg: 0.446 -> 0.471Improved
add ARM to JT + GIM (full model) (ablation)GICD · CoCAF_avg: 0.470 -> 0.504Improved
add JT to GIM + ARM (full model) (ablation)GICD · CoCAF_avg: 0.471 -> 0.504Improved
add JT to GIM (ablation)GICD without ARM · CoCAF_avg: 0.446 -> 0.470Improved
add JT without GIM (ablation)SOD baseline · CoSal2015F_avg: 0.788 -> 0.750Hurt
add JT without GIM (ablation)SOD baseline · CoCAF_avg: 0.420 -> 0.424No clear effect
add JT to GIM + ARM (full model) (ablation)GICD · CoSal2015F_avg: 0.826 -> 0.835Improved
add JT to GIM (ablation)GICD without ARM · CoSal2015F_avg: 0.809 -> 0.795Hurt
use GICD instead of best Co-SOD methodco-saliency detection · CoSal2015F_avg: 11.4% improvementImproved
use GICD instead of best SOD methodco-saliency detection · CoSal2015F_avg: 5.7% improvementImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy